Abstractive Text Summarization On Abstractive 1
评估指标
BERTScore
ROUGE-1
ROUGE-2
ROUGE-L
评测结果
各个模型在此基准测试上的表现结果
模型名称 | BERTScore | ROUGE-1 | ROUGE-2 | ROUGE-L | Paper Title | Repository |
|---|---|---|---|---|---|---|
| IT5-base | 71.06 | 32.88 | 15.53 | 26.7 | BART-IT: An Efficient Sequence-to-Sequence Model for Italian Text Summarization | |
| mBART | - | 38.91 | - | - | Two New Datasets for Italian-Language Abstractive Text Summarization | |
| Pegasus-CNN/DM (eng-it translation) | - | 23.96 | - | - | Two New Datasets for Italian-Language Abstractive Text Summarization | |
| mT5 | 74.69 | 35.04 | 17.41 | 28.68 | BART-IT: An Efficient Sequence-to-Sequence Model for Italian Text Summarization | |
| mBART | 75.86 | 38.91 | 21.41 | 32.08 | BART-IT: An Efficient Sequence-to-Sequence Model for Italian Text Summarization | |
| IT5 | - | 33.78 | - | - | Two New Datasets for Italian-Language Abstractive Text Summarization | |
| Pegasus-XSum (eng-it translation) | - | 21.03 | - | - | Two New Datasets for Italian-Language Abstractive Text Summarization | |
| BART-IT | 75.36 | 37.31 | 19.44 | 30.41 | BART-IT: An Efficient Sequence-to-Sequence Model for Italian Text Summarization |
0 of 8 row(s) selected.